2019
DOI: 10.1007/s40430-019-2010-6
|View full text |Cite
|
Sign up to set email alerts
|

A method for constructing rolling bearing lifetime health indicator based on multi-scale convolutional neural networks

Abstract: The degradation of rolling bearings is complex, and traditional methods of degenerating feature degradation are highly dependent on previous research and expertise. However, the traditional methods' ability for learning the complex relationship between degraded features and large amounts of measured data is limited. So, it is difficult to construct a single health indicator (HI) to predict the degradation state of the bearing. In order to solve this problem, a multi-scale convolutional neural network (MSCNN) i… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
8
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 26 publications
(8 citation statements)
references
References 17 publications
(20 reference statements)
0
8
0
Order By: Relevance
“…This is the case for several of the bearings of condition 2 in the PHM dataset. The sudden failure has previously been reported in the literature and in many cases confirmed as hard to detect and model [4,10,35]. This may be partially alleviated with the use of richer features.…”
Section: Pdm Indicatorsmentioning
confidence: 91%
See 1 more Smart Citation
“…This is the case for several of the bearings of condition 2 in the PHM dataset. The sudden failure has previously been reported in the literature and in many cases confirmed as hard to detect and model [4,10,35]. This may be partially alleviated with the use of richer features.…”
Section: Pdm Indicatorsmentioning
confidence: 91%
“…Previous work has also proposed models with bounded HI curves. Wu et al evaluated four possible degradation curves for the Pronostia dataset [10]. The intermediate HI is modeled with different candidate functions, such as linear, inverse hyperbolic tangent, quadratic, and parabolic.…”
Section: Related Workmentioning
confidence: 99%
“…Too many weights are generally hard to train for the network. Different moving steps in convolution operations are used to obtain features in different scales [21]. A multiscale convolutional neural network that merges the final convolutional layers and the final pooling layer was designed to extract the local and global features for bearing RUL prediction [15].…”
Section: Introductionmentioning
confidence: 99%
“…Bearing, as a supporting part, has the advantages of low frictional resistance, high accuracy and standardization and is widely used in rotary machinery [1][2][3]. Rotating machinery will inevitably produce vibration and noise in the process of operation, among which bearing is one of the most important vibration sources [4,5]. This study analyzes the mechanism of vibration and noise produced by bearings.…”
Section: Introductionmentioning
confidence: 99%